Towards Learning and Explaining Indirect Causal Effects in Neural Networks

Authors: Abbavaram Gowtham Reddy, Saketh Bachu, Harsharaj Pathak, Benin Godfrey L, Varshaneya V, Vineeth N Balasubramanian, Satyanarayan Kar

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments conducted on synthetic and real-world datasets demonstrate that the causal effects learned by our ante-hoc method better approximate the ground truth effects compared to existing methods.
Researcher Affiliation Collaboration Abbavaram Gowtham Reddy1, Saketh Bachu1, Harsharaj Pathak1, Benin L. Godfrey1, Varshaneya V2, Vineeth N. Balasubramanian1, Satyanarayan Kar2 1 Indian Institute of Technology Hyderabad, India 2 Honeywell, Bengaluru, India
Pseudocode Yes Algorithm 1: Pseudocode for training N Ind model
Open Source Code Yes Code is available at https://github.com/gautam0707/Learning-and Explaining-Indirect-Causal-Effects.
Open Datasets Yes We conduct experiments on a synthetic dataset, three well-known real-world benchmark datasets, and three industry-based simulated datasets. ... Auto-MPG: In this experiment, we work on Auto-MPG dataset (Dua and Graff 2017) ... Lung Cancer: In Lung Cancer dataset (Scutari and Denis 2014), whose causal graph is known (see Appendix)... Sachs: Sachs dataset consists of 11 protein types and their causal relationships.
Dataset Splits No The paper mentions using a 'training set' and refers to 'test data point' but does not specify explicit percentages or counts for training, validation, and test splits needed to reproduce the experiment.
Hardware Specification No The paper mentions 'industry-grade flight simulator' for some datasets but does not provide specific hardware details such as GPU/CPU models, memory, or detailed computer specifications used for running experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., Python 3.8, PyTorch 1.9) required to replicate the experiment.
Experiment Setup No The paper does not provide specific experimental setup details such as concrete hyperparameter values (e.g., learning rate, batch size, number of epochs) or optimizer settings in the main text.